Caso

library(tidyverse)
library(lubridate)
library(rvest)

Se importa la tabla “Compustat Global Daily” con los tipos de datos correctos.

global_daily <- read_csv("Compustat_Global_Daily.csv",
  col_types = cols(
    sedol = col_character(), 
    datadate = col_date(format = "%Y%m%d") 
  )
)

Tipo de variable de cada columna

global_daily %>%
  summarise_all(class) %>%
  pivot_longer(everything(), names_to = "column", values_to = "type")

Vista general

global_daily

global_daily %>% 
  count(curcdd) 

observaciones de cada compañía

global_daily %>% 
  count(conm) %>% 
  arrange(conm)

global_daily %>% 
  count(conm) %>% 
  arrange(desc(n))

global_daily %>% 
  filter(curcdd == "EUR") %>% 
  count(conm)

global_daily %>% 
  filter(is.na(qunit)) %>% 
  count(conm)

global_daily %>% 
  count(gsector)

industries

global_daily %>%
  group_by(conm) %>% 
  count(sic) %>% 
  arrange(sic)

global_daily %>% 
  count(sic)

global_daily %>% 
  count(conm) %>% 
  arrange(n) %>% 
  filter(n == 1)

global_daily %>% 
  select(conm, datadate) %>% 
  group_by(conm) %>%
  mutate(n = n()) %>% 
  filter(n == 1)

global_daily %>% 
  select(datadate) %>%
  distinct(datadate) %>% 
  arrange(datadate)

global_daily %>% 
  filter(conm == "WAL MART DE MEXICO SA") %>% 
  select(conm, datadate, cshoc, cshtrd, prccd, prcstd, gsector) %>% 
  mutate(year = year(datadate)) %>% 
  group_by(year) %>% 
  summarise(n = n())

global_daily %>% 
  filter(conm == "WAL MART DE MEXICO SA") %>% 
  select(conm, datadate, cshoc, cshtrd, prccd, prcstd, gsector) %>% 
  arrange(datadate)

global_daily %>% 
  filter(conm == "WAL MART DE MEXICO SA") %>%  
  mutate(year = year(datadate)) %>% 
  filter(year == 1993) %>% 
  arrange(datadate) %>% 
  filter(curcdd == "MXN") 

global_daily %>% 
  count(exchg)

global_daily %>% 
  mutate(year = year(datadate)) %>% 
  #filter(conm == "CEMEX SAB DE CV") %>%
  group_by(year, conm, isin) %>% 
  summarise(num = n())